crewai

Warn

Audited by Snyk on Aug 9, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime workflow where a “researcher” agent is configured with external search/web tools (SerperDevTool/WebsiteSearchTool) that can ingest arbitrary outsider-authored text from search results or scraped web pages without requiring the user to select a specific trusted item first.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 9, 2026, 09:07 AM
Issues
1
Security Audit — snyk — crewai